Black Forest Labs appears to tease FLUX 3, a multimodal model with 20-second video generation
op7418 · x · 2026-07-23
Black Forest Labs appears to be teasing FLUX 3, a full multimodal generation model that would cover images, video, audio, and motion. The leak suggests it may generate single videos up to 20 seconds long, and the poster notes that if it follows the company’s usual pattern, the release could be open source.
Related event: Black Forest Labs Launches FLUX 3: A Unified Multimodal Foundation Model(28 posts)→
More from Multimodal
- 3D ResNet Paper Crosses 3,000 Citations Eight Years After CVPR 2018 — HirokatuKataoka · 2026-09-11
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- RunningHub open-sources H3Lightning, speeding up MiniMax H3 video generation 12x — 智东西 · 2026-09-11
- FastH3-Live hits 22fps: acceleration node benchmarks and the --vram-headroom trick — spartong945 · 2026-09-11
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11